| GitHub Link | Algorithm Used | Simulator Used | Robot | Paper | Notes |
|---|---|---|---|---|---|
| https://github.com/nimazareian/quadruped-rl-locomotion | PPO - SB3 | Mujoco | Unitree Go1 | - | |
| https://github.com/Argo-Robot/quadrupeds_locomotion | PPO | Row 2, Col 3 | Row 2, Col 4 | Multiple papers has been cited. Primary citation: Making Quadrupeds Learning to Walk: From Zero to Hero, a blog (https://federicosarrocco.com/blog/Making-Quadrupeds-Learning-To-Walk) | A very detailed repository that even explains the locomotion task and solution in details. It has also cited multiple papers. |
| https://github.com/iit-DLSLab/gym-quadruped | Your wish | Mujoco | Unitree Go1, Go2, Aliengo, Unitree B2 | Repo from Dynamic Legged Systems Lab - iit. This seems more of like an environment setup for people to test and not a repo where RL exps were conducted. |
|
| https://github.com/fan-ziqi/rl_sar | - | Issac Gym and Sim | Unitree A1, G1, Go2, L4W4, B2 and more (basically legged) |
SAR - Simulation and Real. Has real implementation using ROS. They mostly contain trains models (.pt) files are provided. They are using actuator net | |
| https://github.com/varithpu/Quadruped_Robot_Reinforcement_Learning | PPO - SB3 | PyBullet | Custom Designed Quadruped | Custom designed quad and nothing special | |
| https://github.com/leggedrobotics/legged_gym | The train code is PPO but looks like some custom implementation of RSL (ETH Zurich) | Issac Sim | AnyMal, Unitree and others | https://leggedrobotics.github.io/legged_gym/ (https://arxiv.org/pdf/2109.11978) | Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning |
| https://github.com/leggedrobotics/rsl_rl | Basically the repo for above | Issac Sim | Prolly an alternative to ClearnRL | ||
| https://github.com/nicrusso7/rex-gym | PPO (custom) | Open AI Gym | Like SpotMicro | Might be useful while training our custom printed robot. | |
| https://github.com/dyumanaditya/isaac-quad-loco/tree/main | PPO (custom) | Issac Lab | Your wish | ||
| https://github.com/aadhithya14/Model-Free-Goal-Conditioned-Quadrupedal-Locomotion | PPO | Mujoco (mjcf files found) | Solo v12 | The repo could be used as reference | |
| https://github.com/muye1202/quadruped_locomotion_project | PPO (rsl_rl) | Issac Gym | Unitree Go1 | Visuomotor policy, depth pipeline (too far) | |
| https://github.com/ZaneCodeJourney/quadruped_isaacgym | PPO | Issac Gym | Unitree A1 | Model-free End-to-end Learning of Agile Quadrupedal Locomotion (https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9872190) | Prolly will read the paper first |